A Bootstrapping Approach for Geographic Named Entity Annotation Export

@incollection{14238, abstract = {Geographic named entities can be classified into many sub-types that are useful for applications such as information extraction and question answering. In this paper, we present a bootstrapping algorithm for the task of geographic named entity annotation. In the initial stage, we annotate a raw corpus using seeds. From the initial annotation, boundary patterns are learned and applied to the corpus again to annotate new candidates. Type verification is adopted to reduce over-generation. One sense per discourse principle increases positive instances and also corrects mistaken annotations. As the bootstrapping loop proceeds, the annotated instances are increased gradually and the learned boundary patterns become gradually richer.}, author = {Lee, Seungwoo and Lee, Gary}, citeulike-article-id = {3275597}, citeulike-linkout-0 = {http://www.springerlink.com/content/uxpu0n95fmkt0v2e}, journal = {Information Retrieval Technology}, keywords = {bootstrapping, disambiguation, gazetteer, named-entities, place-names}, pages = {178--189}, posted-at = {2008-09-16 20:26:13}, priority = {2}, title = {A Bootstrapping Approach for Geographic Named Entity Annotation}, url = {http://www.springerlink.com/content/uxpu0n95fmkt0v2e}, year = {2005} }

TY - CHAP ID - 14238 L3 - citeulike-article-id:3275597 N2 - Geographic named entities can be classified into many sub-types that are useful for applications such as information extraction and question answering. In this paper, we present a bootstrapping algorithm for the task of geographic named entity annotation. In the initial stage, we annotate a raw corpus using seeds. From the initial annotation, boundary patterns are learned and applied to the corpus again to annotate new candidates. Type verification is adopted to reduce over-generation. One sense per discourse principle increases positive instances and also corrects mistaken annotations. As the bootstrapping loop proceeds, the annotated instances are increased gradually and the learned boundary patterns become gradually richer. JF - Information Retrieval Technology EP - 189 TI - A Bootstrapping Approach for Geographic Named Entity Annotation SP - 178 KW - bootstrapping KW - disambiguation KW - gazetteer KW - named-entities KW - place-names AU - Lee, Seungwoo AU - Lee, Gary PY - 2005/// UR - http://www.springerlink.com/content/uxpu0n95fmkt0v2e ER -